bytelyst/learning_ai_common_plat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs(ecosystem): refactor delegation to two-way model

Browse Source
This commit is contained in:
Saravana Achu Mac 2026-04-03 18:48:54 -07:00
parent 07189b0f86
commit 094f64c47d
12 changed files with 102 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
docs/ecosystem/ECOSYSTEM_AGENT_OPERATING_MODEL.md
View File

@ -19,6 +19,12 @@ This document is the detailed operating model behind it. Use this file for:
- parallelization rules
- ownership and escalation rules
The repo-native communication loop for delegated work is:
- `TASK.md` = instruction channel
- `STATUS.md` = assigned agent response channel
- `FEEDBACK.md` = reviewer channel
If there is a conflict:
1. Saravana's explicit instruction wins
@ -57,6 +63,8 @@ Agents should use the following hierarchy:
Agents must not invent a parallel process outside these docs.
For delegated work, agents should read the participant folder under [`docs/ecosystem/delegation/`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation) and follow the `TASK.md` / `STATUS.md` / `FEEDBACK.md` loop.
---
## 4. Role Split
@ -118,6 +126,12 @@ Every delegated task must define:
- required verification command
- expected tracker/doc update if the task changes completion state
Every active participant folder must also contain:
- `TASK.md`
- `STATUS.md`
- `FEEDBACK.md`
### What Codex Should Keep
Codex should keep work local when it:

33
docs/ecosystem/delegation/README.md
View File

@ -7,12 +7,20 @@
## Current Delegation Set
- [`saravana/COORDINATION.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/saravana/COORDINATION.md)
- [`codex/PHASE1_INTEGRATION_REVIEW.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/codex/PHASE1_INTEGRATION_REVIEW.md)
- [`windsurf/NOTELETT_PHASE1_VERIFICATION.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/windsurf/NOTELETT_PHASE1_VERIFICATION.md)
- [`cursor/MINDLYST_PHASE1_VERIFICATION.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/cursor/MINDLYST_PHASE1_VERIFICATION.md)
- [`saravana/TASK.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/saravana/TASK.md)
- [`saravana/STATUS.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/saravana/STATUS.md)
- [`saravana/FEEDBACK.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/saravana/FEEDBACK.md)
- [`codex/TASK.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/codex/TASK.md)
- [`codex/STATUS.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/codex/STATUS.md)
- [`codex/FEEDBACK.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/codex/FEEDBACK.md)
- [`windsurf/TASK.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/windsurf/TASK.md)
- [`windsurf/STATUS.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/windsurf/STATUS.md)
- [`windsurf/FEEDBACK.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/windsurf/FEEDBACK.md)
- [`cursor/TASK.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/cursor/TASK.md)
- [`cursor/STATUS.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/cursor/STATUS.md)
- [`cursor/FEEDBACK.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/cursor/FEEDBACK.md)
- [`TWO_WAY_COMMUNICATION_REFACTOR_PLAN.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/TWO_WAY_COMMUNICATION_REFACTOR_PLAN.md)
- review this before refactoring the participant folders into the 3-file communication loop
- historical refactor blueprint for how the 3-file communication loop was introduced
---
@ -21,22 +29,23 @@
Give an agent a one-liner in this form:
```bash
git pull origin main && read the task file at <absolute-path> and execute it exactly within its ownership boundaries
git pull origin main && read <participant>/TASK.md and <participant>/FEEDBACK.md, execute within ownership boundaries, and write progress back to <participant>/STATUS.md
```
Example:
```bash
git pull origin main && read /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/windsurf/NOTELETT_PHASE1_VERIFICATION.md and execute it exactly within its ownership boundaries
git pull origin main && read /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/windsurf/TASK.md and /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/windsurf/FEEDBACK.md, execute within ownership boundaries, and update /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/windsurf/STATUS.md
```
---
## Rules
- task files must stay bounded
- task files must name owned files or modules
- task files must name do-not-touch boundaries
- task files must include verification expectations
- `TASK.md` must stay bounded
- `TASK.md` must name owned files or modules
- `TASK.md` must name do-not-touch boundaries
- `TASK.md` must include verification expectations
- assigned agents must update `STATUS.md` instead of reporting completion only in chat
- Codex reviews delegated outputs before ecosystem completion is claimed
- each participant folder may also contain `FEEDBACK.md` for durable review notes and process corrections
- each participant folder must contain `TASK.md`, `STATUS.md`, and `FEEDBACK.md`

2
docs/ecosystem/delegation/TWO_WAY_COMMUNICATION_REFACTOR_PLAN.md
View File

@ -1,6 +1,6 @@
# Two-Way Delegation Refactor Plan
> **Status:** Proposed
> **Status:** Implemented
> **Owner:** `learning_ai_common_plat`
> **Goal:** Refactor the delegation folders into a stable two-way communication model before broader multi-agent execution.

15
docs/ecosystem/delegation/codex/STATUS.md Normal file
View File

@ -0,0 +1,15 @@
# Status
- **Task:** [`TASK.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/codex/TASK.md)
- **Owner:** Codex
- **Status:** in-progress
- **Updated at:** 2026-04-04T00:00:00Z
- **Latest commit:** `4cc6899`
- **Verification command:** `/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/node_modules/.bin/vitest run src/lib/ecosystem-phase1.test.ts src/__tests__/api-memory.test.ts`
- **Verification result:** pass
- **Blocker:** waiting on final NoteLett verification result before Phase 1 closeout
## Notes For Reviewer
- MindLyst focused verification is confirmed.
- Final Codex closeout still depends on Windsurf's NoteLett result.

4
docs/ecosystem/delegation/codex/PHASE1_INTEGRATION_REVIEW.md → docs/ecosystem/delegation/codex/TASK.md
View File

@ -1,4 +1,4 @@
# Codex Phase 1 Integration Review
# Codex Task
> **Role:** Codex
> **Repo Lead:** cross-repo
@ -48,5 +48,5 @@ Use this closeout gate when the delegated results arrive:
## Launch One-Liner
```bash
git pull origin main && read /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/codex/PHASE1_INTEGRATION_REVIEW.md and execute it exactly within its ownership boundaries
git pull origin main && read /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/codex/TASK.md and /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/codex/FEEDBACK.md, execute within ownership boundaries, and update /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/codex/STATUS.md
```

2
docs/ecosystem/delegation/cursor/FEEDBACK.md
View File

@ -7,7 +7,7 @@
## Entry 1: MindLyst Phase 1 Verification Review
- **Task file:** [`MINDLYST_PHASE1_VERIFICATION.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/cursor/MINDLYST_PHASE1_VERIFICATION.md)
- **Task file:** [`TASK.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/cursor/TASK.md)
- **Reviewed by:** Codex
- **Review status:** approved-with-follow-up
- **Related commit:** [`49796b1`](https://github.com/saravanakumardb1/learning_multimodal_memory_agents/commit/49796b1)

14
docs/ecosystem/delegation/cursor/STATUS.md Normal file
View File

@ -0,0 +1,14 @@
# Status
- **Task:** [`TASK.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/cursor/TASK.md)
- **Owner:** Cursor
- **Status:** done
- **Updated at:** 2026-04-04T00:00:00Z
- **Latest commit:** `49796b1`
- **Verification command:** `/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/node_modules/.bin/vitest run src/lib/ecosystem-phase1.test.ts src/__tests__/api-memory.test.ts`
- **Verification result:** pass
- **Blocker:** package-local `npm run test:phase1` is still not self-sufficient in this clone because local `vitest` is missing
## Notes For Reviewer
- Cursor improved the local package path but Codex performed the final focused verification.

4
docs/ecosystem/delegation/cursor/MINDLYST_PHASE1_VERIFICATION.md → docs/ecosystem/delegation/cursor/TASK.md
View File

@ -1,4 +1,4 @@
# Cursor Task: MindLyst Phase 1 Verification
# Cursor Task
> **Role:** Cursor
> **Repo:** `learning_multimodal_memory_agents`
@ -61,5 +61,5 @@ Completion requires one of these:
## Launch One-Liner
```bash
git pull origin main && read /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/cursor/MINDLYST_PHASE1_VERIFICATION.md and execute it exactly within its ownership boundaries
git pull origin main && read /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/cursor/TASK.md and /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/cursor/FEEDBACK.md, execute within ownership boundaries, and update /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/cursor/STATUS.md
```

14
docs/ecosystem/delegation/saravana/STATUS.md Normal file
View File

@ -0,0 +1,14 @@
# Status
- **Task:** [`TASK.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/saravana/TASK.md)
- **Owner:** Saravana
- **Status:** in-progress
- **Updated at:** 2026-04-04T00:00:00Z
- **Latest commit:** none
- **Verification command:** none
- **Verification result:** not-run
- **Blocker:** none
## Notes For Reviewer
- Saravana is coordinating the Phase 1 closeout sequence.

4
docs/ecosystem/delegation/saravana/COORDINATION.md → docs/ecosystem/delegation/saravana/TASK.md
View File

@ -1,4 +1,4 @@
# Saravana Coordination Task
# Saravana Task
> **Role:** Saravana
> **Purpose:** sequencing, approval, and merge authority for the current Phase 1 completion work
@ -28,5 +28,5 @@ Coordinate the final Phase 1 verification push without changing the technical co
## Launch One-Liner
```bash
git pull origin main && read /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/saravana/COORDINATION.md and use it as the current coordination brief
git pull origin main && read /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/saravana/TASK.md and /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/saravana/FEEDBACK.md, then use /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/saravana/STATUS.md as the coordination status log
```

14
docs/ecosystem/delegation/windsurf/STATUS.md Normal file
View File

@ -0,0 +1,14 @@
# Status
- **Task:** [`TASK.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/windsurf/TASK.md)
- **Owner:** Windsurf
- **Status:** not-started
- **Updated at:** 2026-04-04T00:00:00Z
- **Latest commit:** none
- **Verification command:** `pnpm --filter @notelett/backend run test`
- **Verification result:** not-run
- **Blocker:** pending Windsurf execution
## Notes For Reviewer
- This remains the open verification blocker for full Phase 1 closeout.

4
docs/ecosystem/delegation/windsurf/NOTELETT_PHASE1_VERIFICATION.md → docs/ecosystem/delegation/windsurf/TASK.md
View File

@ -1,4 +1,4 @@
# Windsurf Task: NoteLett Phase 1 Verification
# Windsurf Task
> **Role:** Windsurf
> **Repo:** `learning_ai_notes`
@ -56,5 +56,5 @@ Return the result to Codex for review before claiming completion.
## Launch One-Liner
```bash
git pull origin main && read /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/windsurf/NOTELETT_PHASE1_VERIFICATION.md and execute it exactly within its ownership boundaries
git pull origin main && read /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/windsurf/TASK.md and /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/windsurf/FEEDBACK.md, execute within ownership boundaries, and update /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/windsurf/STATUS.md
```